Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 63 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.3243. Min Range: -1.3243

Max Act: 1.3243. Min Act: -0.0001

Data Index: 416068 (C4 (Web Text))

Max Activating Token Index: 1006

Text #1

Max Range: 1.3243. Min Range: -1.3243

Max Act: 1.0710. Min Act: -0.0001

Data Index: 1240858 (C4 (Web Text))

Max Activating Token Index: 496

Text #2

Max Range: 1.3243. Min Range: -1.3243

Max Act: 1.0959. Min Act: -0.0001

Data Index: 683133 (C4 (Web Text))

Max Activating Token Index: 1002

Text #3

Max Range: 1.3243. Min Range: -1.3243

Max Act: 1.0437. Min Act: -0.0001

Data Index: 892055 (C4 (Web Text))

Max Activating Token Index: 471

Text #4

Max Range: 1.3243. Min Range: -1.3243

Max Act: 0.9631. Min Act: -0.0001

Data Index: 1119619 (C4 (Web Text))

Max Activating Token Index: 919

Text #5

Max Range: 1.3243. Min Range: -1.3243

Max Act: 0.8773. Min Act: -0.0001

Data Index: 212553 (C4 (Web Text))

Max Activating Token Index: 627

Text #6

Max Range: 1.3243. Min Range: -1.3243

Max Act: 0.8540. Min Act: -0.0001

Data Index: 195382 (C4 (Web Text))

Max Activating Token Index: 191

Text #7

Max Range: 1.3243. Min Range: -1.3243

Max Act: 0.9947. Min Act: -0.0001

Data Index: 1092473 (C4 (Web Text))

Max Activating Token Index: 227

Text #8

Max Range: 1.3243. Min Range: -1.3243

Max Act: 0.8934. Min Act: -0.0001

Data Index: 649297 (C4 (Web Text))

Max Activating Token Index: 900

Text #9

Max Range: 1.3243. Min Range: -1.3243

Max Act: 0.8829. Min Act: -0.0001

Data Index: 1051774 (C4 (Web Text))

Max Activating Token Index: 975

Text #10

Max Range: 1.3243. Min Range: -1.3243

Max Act: 0.9013. Min Act: -0.0001

Data Index: 1305856 (C4 (Web Text))

Max Activating Token Index: 705

Text #11

Max Range: 1.3243. Min Range: -1.3243

Max Act: 0.8305. Min Act: -0.0001

Data Index: 634050 (C4 (Web Text))

Max Activating Token Index: 854

Text #12

Max Range: 1.3243. Min Range: -1.3243

Max Act: 0.8405. Min Act: -0.0001

Data Index: 657395 (C4 (Web Text))

Max Activating Token Index: 663

Text #13

Max Range: 1.3243. Min Range: -1.3243

Max Act: 0.8859. Min Act: -0.0001

Data Index: 842336 (C4 (Web Text))

Max Activating Token Index: 75

Text #14

Max Range: 1.3243. Min Range: -1.3243

Max Act: 0.8186. Min Act: -0.0001

Data Index: 967398 (C4 (Web Text))

Max Activating Token Index: 643

Text #15

Max Range: 1.3243. Min Range: -1.3243

Max Act: 0.8622. Min Act: -0.0001

Data Index: 28171 (C4 (Web Text))

Max Activating Token Index: 728

Text #16

Max Range: 1.3243. Min Range: -1.3243

Max Act: 0.8902. Min Act: -0.0001

Data Index: 51300 (C4 (Web Text))

Max Activating Token Index: 111

Text #17

Max Range: 1.3243. Min Range: -1.3243

Max Act: 0.8900. Min Act: -0.0001

Data Index: 266683 (C4 (Web Text))

Max Activating Token Index: 68

Text #18

Max Range: 1.3243. Min Range: -1.3243

Max Act: 0.7902. Min Act: -0.0001

Data Index: 312394 (C4 (Web Text))

Max Activating Token Index: 785

Text #19

Max Range: 1.3243. Min Range: -1.3243

Max Act: 0.9365. Min Act: -0.0001

Data Index: 972191 (C4 (Web Text))

Max Activating Token Index: 77